TY - GEN
T1 - Slow Start Transition in Participatory Sensing Applications
AU - Saremi, Fatemeh
AU - Abdelzaher, Tarek
N1 - Funding Information:
This research was sponsored in part by IBM Research and NSF Grants CNS 10-59294, CNS 10-40380 and CNS 13-45266.
PY - 2017/1/11
Y1 - 2017/1/11
N2 - In this paper, we present the "Slow Start Problem" in participatory sensing applications where a service is provided based on data collected by participants. The slow start problem refers to the initial stage in participatory sensing service deployment, during which service adoption remains sparse and, hence, the collected data does not offer adequate coverage. Predictive models, learned from data, offer a way to generalize from sparse observations, but the models themselves need to be statistically reliable to offer a reliable service. To achieve service reliability, this paper offers a modeling approach, where simpler models are used initially, gradually transitioning to more elaborate models, when enough data is collected. A key challenge and contribution of the work is to time model transitions correctly to provide theoretical guarantees on modeling error. Our technique takes a holistic approach in bounding modeling error as opposed to prior statistical approaches that bound the error of a single model component at a time. This technique is tested in the context of a vehicular participatory sensing application, called GreenGPS, where participant data is used to build models that predict fuel consumption of vehicles on different routes for the purposes of choosing the most fuel-efficient route for each vehicle (as opposed to the shortest or fastest). We show that our approach significantly reduces prediction error in the initial stages of deployment.
AB - In this paper, we present the "Slow Start Problem" in participatory sensing applications where a service is provided based on data collected by participants. The slow start problem refers to the initial stage in participatory sensing service deployment, during which service adoption remains sparse and, hence, the collected data does not offer adequate coverage. Predictive models, learned from data, offer a way to generalize from sparse observations, but the models themselves need to be statistically reliable to offer a reliable service. To achieve service reliability, this paper offers a modeling approach, where simpler models are used initially, gradually transitioning to more elaborate models, when enough data is collected. A key challenge and contribution of the work is to time model transitions correctly to provide theoretical guarantees on modeling error. Our technique takes a holistic approach in bounding modeling error as opposed to prior statistical approaches that bound the error of a single model component at a time. This technique is tested in the context of a vehicular participatory sensing application, called GreenGPS, where participant data is used to build models that predict fuel consumption of vehicles on different routes for the purposes of choosing the most fuel-efficient route for each vehicle (as opposed to the shortest or fastest). We show that our approach significantly reduces prediction error in the initial stages of deployment.
KW - Application
KW - Modeling
KW - Participatory Sensing
KW - Reliability
UR - http://www.scopus.com/inward/record.url?scp=85013230946&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85013230946&partnerID=8YFLogxK
U2 - 10.1109/MASS.2016.013
DO - 10.1109/MASS.2016.013
M3 - Conference contribution
AN - SCOPUS:85013230946
T3 - Proceedings - 2016 IEEE 13th International Conference on Mobile Ad Hoc and Sensor Systems, MASS 2016
SP - 10
EP - 18
BT - Proceedings - 2016 IEEE 13th International Conference on Mobile Ad Hoc and Sensor Systems, MASS 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 13th IEEE International Conference on Mobile Ad Hoc and Sensor Systems, MASS 2016
Y2 - 10 October 2016 through 13 October 2016
ER -